QuGAN: A Quantum State Fidelity based Generative Adversarial Network

TL;DR

QuGAN introduces a quantum GAN architecture that leverages quantum state fidelity and swap test techniques to achieve stable convergence, reduced parameters, and improved performance over existing quantum GANs.

Contribution

This paper presents QuGAN, a novel quantum GAN architecture utilizing quantum state fidelity and swap tests, with significantly fewer parameters and better performance than prior quantum GANs.

Findings

Achieves 94.98% reduction in parameters compared to classical GANs.

Outperforms existing quantum GANs with a 48.33% improvement in similarity metrics.

Provides stable convergence and quantum-state based gradients for efficient training.

Abstract

Tremendous progress has been witnessed in artificial intelligence where neural network backed deep learning systems have been used, with applications in almost every domain. As a representative deep learning framework, Generative Adversarial Network (GAN) has been widely used for generating artificial images, text-to-image or image augmentation across areas of science, arts and video games. However, GANs are computationally expensive, sometimes computationally prohibitive. Furthermore, training GANs may suffer from convergence failure and modal collapse. Aiming at the acceleration of use cases for practical quantum computers, we propose QuGAN, a quantum GAN architecture that provides stable convergence, quantum-state based gradients and significantly reduced parameter sets. The QuGAN architecture runs both the discriminator and the generator purely on quantum state fidelity and utilizes the swap test on qubits to calculate the values of quantum-based loss functions. Built on quantum layers, QuGAN achieves similar performance with a 94.98% reduction on the parameter set when compared to classical GANs. With the same number of parameters, additionally, QuGAN outperforms state-of-the-art quantum based GANs in the literature providing a 48.33% improvement in system performance compared to others attaining less than 0.5% in terms of similarity between generated distributions and original data sets. QuGAN code is released at https://github.com/yingmao/Quantum-Generative-Adversarial-Network